NIPS ˙08 Workshop: Beyond Search - Computational Intelligence for the Web

Interactively Optimizing Information Systems as a Dueling Bandits Problem

author: Thorsten Joachims, Cornell University
author: Yisong Yue, Department of Computer Science, Cornell University
published: Dec. 20, 2008, recorded: December 2008, views: 110

Turn off the lights

You might be experiencing some problems with Your Video player.

Slides

Slides
0:00	Interactively Optimizing Information Systems as a Dueling Bandits Problem
0:08	Batch Learning for IR
0:25	Limitations of Batch Learning
1:27	Implicit User Feedback
2:15	Outline
2:50	Interpreting Implicit Feedback
3:44	Team-Game Interleaving1.
5:03	Dueling Bandits Problem (1)
5:42	Dueling Bandits Problem (2)
7:04	Modeling Assumptions
8:23	Probability Functions
9:34	Dueling Bandit Gradient Descent
11:03	Analysis (Sketch) (1)
11:38	Analysis (Sketch) (2)
12:03	Regret Bound
12:41	Practical Considerations
13:23	Regret comparison DBGD vs BGD
14:25	NDCG(at)10 as Vaue Function
15:34	What Next?
16:28	- questions
17:21	Probability Functions
17:50	Analysis (Sketch) (1)

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.

Description

We present an online learning framework tailored towards real-time learning from observed user behavior in search engines and other information access systems. In particular, we only require pairwise comparisons which were shown to be reliably inferred from implicit feedback [4, 3]. We will present an algorithm with theoretical guarantees as well as simulation results.